Semi-supervised Liver Segmentation and Patch-based Fibrosis Staging with Registration-aided Multi-parametric MRI

2026-02-10

AI Summary

This work addresses the challenges of scarce annotations, modality discrepancies, and domain shift in precise segmentation and staging of liver fibrosis using multiparametric MRI. To this end, we propose a multitask deep learning framework that integrates semi-supervised segmentation with image registration to enhance liver region localization accuracy, and introduces an interpretable patch-level classification strategy for fibrosis staging. The method effectively leverages limited labeled data alongside abundant unlabeled multimodal MRI scans—including T1-, T2-weighted, diffusion-weighted imaging (DWI), and gadolinium-enhanced dynamic (GED) sequences—and is evaluated on the independent test set of the CARE Liver 2025 Challenge. Supporting both 3-channel and 7-channel inputs, our approach demonstrates strong generalization performance under both in-distribution (ID) and out-of-distribution (OOD) scenarios.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Liver fibrosis poses a substantial challenge in clinical practice, emphasizing the necessity for precise liver segmentation and accurate disease staging. Based on the CARE Liver 2025 Track 4 Challenge, this study introduces a multi-task deep learning framework developed for liver segmentation (LiSeg) and liver fibrosis staging (LiFS) using multiparametric MRI. The LiSeg phase addresses the challenge of limited annotated images and the complexities of multi-parametric MRI data by employing a semi-supervised learning model that integrates image segmentation and registration. By leveraging both labeled and unlabeled data, the model overcomes the difficulties introduced by domain shifts and variations across modalities. In the LiFS phase, we employed a patchbased method which allows the visualization of liver fibrosis stages based on the classification outputs. Our approach effectively handles multimodality imaging data, limited labels, and domain shifts. The proposed method has been tested by the challenge organizer on an independent test set that includes in-distribution (ID) and out-of-distribution (OOD) cases using three-channel MRIs (T1, T2, DWI) and seven-channel MRIs (T1, T2, DWI, GED1-GED4). The code is freely available. Github link: https://github.com/mileywang3061/Care-Liver

Problem

• liver fibrosis
• liver segmentation
• semi-supervised learning
• multi-parametric MRI
• domain shift

Innovation

• semi-supervised learning
• multi-parametric MRI
• image registration
• patch-based classification
• liver fibrosis staging